aboutsummaryrefslogtreecommitdiff
path: root/tools/perf/util/c++/clang.cpp
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /tools/perf/util/c++/clang.cpp
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to 'tools/perf/util/c++/clang.cpp')
-rw-r--r--tools/perf/util/c++/clang.cpp225
1 files changed, 225 insertions, 0 deletions
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
new file mode 100644
index 000000000..1aad7d6d3
--- /dev/null
+++ b/tools/perf/util/c++/clang.cpp
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * llvm C frontend for perf. Support dynamically compile C file
+ *
+ * Inspired by clang example code:
+ * http://llvm.org/svn/llvm-project/cfe/trunk/examples/clang-interpreter/main.cpp
+ *
+ * Copyright (C) 2016 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2016 Huawei Inc.
+ */
+
+#include "clang/Basic/Version.h"
+#include "clang/CodeGen/CodeGenAction.h"
+#include "clang/Frontend/CompilerInvocation.h"
+#include "clang/Frontend/CompilerInstance.h"
+#include "clang/Frontend/TextDiagnosticPrinter.h"
+#include "clang/Tooling/Tooling.h"
+#include "llvm/IR/LegacyPassManager.h"
+#include "llvm/IR/Module.h"
+#include "llvm/Option/Option.h"
+#include "llvm/Support/FileSystem.h"
+#include "llvm/Support/ManagedStatic.h"
+#if CLANG_VERSION_MAJOR >= 14
+#include "llvm/MC/TargetRegistry.h"
+#else
+#include "llvm/Support/TargetRegistry.h"
+#endif
+#include "llvm/Support/TargetSelect.h"
+#include "llvm/Target/TargetMachine.h"
+#include "llvm/Target/TargetOptions.h"
+#include <memory>
+
+#include "clang.h"
+#include "clang-c.h"
+
+namespace perf {
+
+static std::unique_ptr<llvm::LLVMContext> LLVMCtx;
+
+using namespace clang;
+
+static CompilerInvocation *
+createCompilerInvocation(llvm::opt::ArgStringList CFlags, StringRef& Path,
+ DiagnosticsEngine& Diags)
+{
+ llvm::opt::ArgStringList CCArgs {
+ "-cc1",
+ "-triple", "bpf-pc-linux",
+ "-fsyntax-only",
+ "-O2",
+ "-nostdsysteminc",
+ "-nobuiltininc",
+ "-vectorize-loops",
+ "-vectorize-slp",
+ "-Wno-unused-value",
+ "-Wno-pointer-sign",
+ "-x", "c"};
+
+ CCArgs.append(CFlags.begin(), CFlags.end());
+ CompilerInvocation *CI = tooling::newInvocation(&Diags, CCArgs
+#if CLANG_VERSION_MAJOR >= 11
+ ,/*BinaryName=*/nullptr
+#endif
+ );
+
+ FrontendOptions& Opts = CI->getFrontendOpts();
+ Opts.Inputs.clear();
+ Opts.Inputs.emplace_back(Path,
+ FrontendOptions::getInputKindForExtension("c"));
+ return CI;
+}
+
+static std::unique_ptr<llvm::Module>
+getModuleFromSource(llvm::opt::ArgStringList CFlags,
+ StringRef Path, IntrusiveRefCntPtr<vfs::FileSystem> VFS)
+{
+ CompilerInstance Clang;
+ Clang.createDiagnostics();
+
+#if CLANG_VERSION_MAJOR < 9
+ Clang.setVirtualFileSystem(&*VFS);
+#else
+ Clang.createFileManager(&*VFS);
+#endif
+
+#if CLANG_VERSION_MAJOR < 4
+ IntrusiveRefCntPtr<CompilerInvocation> CI =
+ createCompilerInvocation(std::move(CFlags), Path,
+ Clang.getDiagnostics());
+ Clang.setInvocation(&*CI);
+#else
+ std::shared_ptr<CompilerInvocation> CI(
+ createCompilerInvocation(std::move(CFlags), Path,
+ Clang.getDiagnostics()));
+ Clang.setInvocation(CI);
+#endif
+
+ std::unique_ptr<CodeGenAction> Act(new EmitLLVMOnlyAction(&*LLVMCtx));
+ if (!Clang.ExecuteAction(*Act))
+ return std::unique_ptr<llvm::Module>(nullptr);
+
+ return Act->takeModule();
+}
+
+std::unique_ptr<llvm::Module>
+getModuleFromSource(llvm::opt::ArgStringList CFlags,
+ StringRef Name, StringRef Content)
+{
+ using namespace vfs;
+
+ llvm::IntrusiveRefCntPtr<OverlayFileSystem> OverlayFS(
+ new OverlayFileSystem(getRealFileSystem()));
+ llvm::IntrusiveRefCntPtr<InMemoryFileSystem> MemFS(
+ new InMemoryFileSystem(true));
+
+ /*
+ * pushOverlay helps setting working dir for MemFS. Must call
+ * before addFile.
+ */
+ OverlayFS->pushOverlay(MemFS);
+ MemFS->addFile(Twine(Name), 0, llvm::MemoryBuffer::getMemBuffer(Content));
+
+ return getModuleFromSource(std::move(CFlags), Name, OverlayFS);
+}
+
+std::unique_ptr<llvm::Module>
+getModuleFromSource(llvm::opt::ArgStringList CFlags, StringRef Path)
+{
+ IntrusiveRefCntPtr<vfs::FileSystem> VFS(vfs::getRealFileSystem());
+ return getModuleFromSource(std::move(CFlags), Path, VFS);
+}
+
+std::unique_ptr<llvm::SmallVectorImpl<char>>
+getBPFObjectFromModule(llvm::Module *Module)
+{
+ using namespace llvm;
+
+ std::string TargetTriple("bpf-pc-linux");
+ std::string Error;
+ const Target* Target = TargetRegistry::lookupTarget(TargetTriple, Error);
+ if (!Target) {
+ llvm::errs() << Error;
+ return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);
+ }
+
+ llvm::TargetOptions Opt;
+ TargetMachine *TargetMachine =
+ Target->createTargetMachine(TargetTriple,
+ "generic", "",
+ Opt, Reloc::Static);
+
+ Module->setDataLayout(TargetMachine->createDataLayout());
+ Module->setTargetTriple(TargetTriple);
+
+ std::unique_ptr<SmallVectorImpl<char>> Buffer(new SmallVector<char, 0>());
+ raw_svector_ostream ostream(*Buffer);
+
+ legacy::PassManager PM;
+ bool NotAdded;
+ NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream
+#if CLANG_VERSION_MAJOR >= 7
+ , /*DwoOut=*/nullptr
+#endif
+#if CLANG_VERSION_MAJOR < 10
+ , TargetMachine::CGFT_ObjectFile
+#else
+ , llvm::CGFT_ObjectFile
+#endif
+ );
+ if (NotAdded) {
+ llvm::errs() << "TargetMachine can't emit a file of this type\n";
+ return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);
+ }
+ PM.run(*Module);
+
+ return Buffer;
+}
+
+}
+
+extern "C" {
+void perf_clang__init(void)
+{
+ perf::LLVMCtx.reset(new llvm::LLVMContext());
+ LLVMInitializeBPFTargetInfo();
+ LLVMInitializeBPFTarget();
+ LLVMInitializeBPFTargetMC();
+ LLVMInitializeBPFAsmPrinter();
+}
+
+void perf_clang__cleanup(void)
+{
+ perf::LLVMCtx.reset(nullptr);
+ llvm::llvm_shutdown();
+}
+
+int perf_clang__compile_bpf(const char *filename,
+ void **p_obj_buf,
+ size_t *p_obj_buf_sz)
+{
+ using namespace perf;
+
+ if (!p_obj_buf || !p_obj_buf_sz)
+ return -EINVAL;
+
+ llvm::opt::ArgStringList CFlags;
+ auto M = getModuleFromSource(std::move(CFlags), filename);
+ if (!M)
+ return -EINVAL;
+ auto O = getBPFObjectFromModule(&*M);
+ if (!O)
+ return -EINVAL;
+
+ size_t size = O->size_in_bytes();
+ void *buffer;
+
+ buffer = malloc(size);
+ if (!buffer)
+ return -ENOMEM;
+ memcpy(buffer, O->data(), size);
+ *p_obj_buf = buffer;
+ *p_obj_buf_sz = size;
+ return 0;
+}
+}